English
Related papers

Related papers: Sound Value Iteration for Simple Stochastic Games

200 papers

We propose empirical dynamic programming algorithms for Markov decision processes (MDPs). In these algorithms, the exact expectation in the Bellman operator in classical value iteration is replaced by an empirical estimate to get `empirical…

Optimization and Control · Mathematics 2013-11-26 William B. Haskell , Rahul Jain , Dileep Kalathil

For model checking stochastic games (SGs), bounded value iteration (BVI) algorithms have gained attention as efficient approximate methods with rigorous precision guarantees. However, BVI may not terminate or converge when the target SG…

Logic in Computer Science · Computer Science 2025-11-05 Kittiphon Phalakarn , Yun Chen Tsai , Ichiro Hasuo

We introduce new planning and reinforcement learning algorithms for discounted MDPs that utilize an approximate model of the environment to accelerate the convergence of the value function. Inspired by the splitting approach in numerical…

Machine Learning · Computer Science 2022-11-28 Amin Rakhsha , Andrew Wang , Mohammad Ghavamzadeh , Amir-massoud Farahmand

We study the problem of learning policies that maximize cumulative reward while satisfying safety constraints, even when the real environment differs from a simulator or nominal model. We focus on robust constrained Markov decision…

Machine Learning · Computer Science 2025-11-12 Sourav Ganguly , Arnob Ghosh

Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in which states of the system are observable only indirectly, via a…

Artificial Intelligence · Computer Science 2011-06-02 M. Hauskrecht

Policy iteration is a family of algorithms that are used to find an optimal policy for a given Markov Decision Problem (MDP). Simple Policy iteration (SPI) is a type of policy iteration where the strategy is to change the policy at exactly…

Machine Learning · Computer Science 2019-12-02 Sarthak Consul , Bhishma Dedhia , Kumar Ashutosh , Parthasarathi Khirwadkar

This paper analyzes reinforcement learning (RL) algorithms for Markov decision processes (MDPs) under the average-reward criterion. We focus on Q-learning algorithms based on relative value iteration (RVI), which are model-free stochastic…

Machine Learning · Computer Science 2024-08-30 Yi Wan , Huizhen Yu , Richard S. Sutton

A classical problem in matrix computations is the efficient and reliable approximation of a given matrix by a matrix of lower rank. The truncated singular value decomposition (SVD) is known to provide the best such approximation for any…

Numerical Analysis · Mathematics 2014-08-12 Ming Gu

Semi-implicit variational inference (SIVI) greatly enriches the expressiveness of variational families by considering implicit variational distributions defined in a hierarchical manner. However, due to the intractable densities of…

Machine Learning · Statistics 2023-08-22 Longlin Yu , Cheng Zhang

One-counter MDPs (OC-MDPs) and one-counter simple stochastic games (OC-SSGs) are 1-player, and 2-player turn-based zero-sum, stochastic games played on the transition graph of classic one-counter automata (equivalently, pushdown automata…

Computer Science and Game Theory · Computer Science 2011-07-21 Tomáš Brázdil , Václav Brožek , Kousha Etessami , Antonín Kučera

Preferences play a key role in determining what goals/constraints to satisfy when not all constraints can be satisfied simultaneously. In this paper, we study how to synthesize preference satisfying plans in stochastic systems, modeled as…

Artificial Intelligence · Computer Science 2022-10-06 Abhishek N. Kulkarni , Jie Fu

State-of-the-art methods for solving 2-player zero-sum imperfect information games rely on linear programming or regret minimization, though not on dynamic programming (DP) or heuristic search (HS), while the latter are often at the core of…

Artificial Intelligence · Computer Science 2022-10-27 Aurélien Delage , Olivier Buffet , Jilles S. Dibangoye , Abdallah Saffidine

Value iteration (VI) is a ubiquitous algorithm for optimal control, planning, and reinforcement learning schemes. Under the right assumptions, VI is a vital tool to generate inputs with desirable properties for the controlled system, like…

Optimization and Control · Mathematics 2020-11-23 Mathieu Granzotto , Romain Postoyan , Dragan Nešić , Lucian Buşoniu , Jamal Daafouz

Policy Iteration (PI) is a widely used family of algorithms to compute optimal policies for Markov Decision Problems (MDPs). We derive upper bounds on the running time of PI on Deterministic MDPs (DMDPs): the class of MDPs in which every…

Discrete Mathematics · Computer Science 2023-10-10 Ritesh Goenka , Eashan Gupta , Sushil Khyalia , Pratyush Agarwal , Mulinti Shaik Wajid , Shivaram Kalyanakrishnan

We present a general framework for applying learning algorithms and heuristical guidance to the verification of Markov decision processes (MDPs). The primary goal of our techniques is to improve performance by avoiding an exhaustive…

Reinforcement learning in non-stationary environments is challenging due to abrupt and unpredictable changes in dynamics, often causing traditional algorithms to fail to converge. However, in many real-world cases, non-stationarity has some…

Machine Learning · Computer Science 2025-03-25 Mohsen Amiri , Sindri Magnússon

When solving finite-sum minimization problems, two common alternatives to stochastic gradient descent (SGD) with theoretical benefits are random reshuffling (SGD-RR) and shuffle-once (SGD-SO), in which functions are sampled in cycles…

Optimization and Control · Mathematics 2022-06-02 Carles Domingo-Enrich

We study average-reward Markov decision processes (AMDPs) and develop novel first-order methods with strong theoretical guarantees for both policy optimization and policy evaluation. Compared with intensive research efforts in finite sample…

Machine Learning · Computer Science 2024-10-01 Tianjiao Li , Feiyang Wu , Guanghui Lan

In this paper, we present a novel stochastic method for solving variational inequalities (VI) in the context of Markovian noise. By leveraging Extragradient technique, we can productively solve VI optimization problems characterized by…

Optimization and Control · Mathematics 2026-05-18 Vladimir Solodkin , Michael Ermoshin , Roman Gavrilenko , Aleksandr Beznosikov

Standard Markov decision process (MDP) and reinforcement learning algorithms optimize the policy with respect to the expected gain. We propose an algorithm which enables to optimize an alternative objective: the probability that the gain is…

Machine Learning · Computer Science 2023-03-06 Vincent Corlay , Jean-Christophe Sibel